基礎知識
python知識：
import os,shutil
shutil.rmtree("C:\\Users\\yangwj\\Desktop\\test") #刪除目錄
os.remove("C:\\Users\\yangwj\\Desktop\\replay_pid28076.log") # 刪除文件
os.path.isfile() # 判斷是否為文件
os.listdir() # 列出路徑下的目錄
1、從攝像頭獲取人臉圖片
import dlib # 人臉處理的庫 Dlib import numpy as np # 數據處理的庫 Numpy import cv2 # 圖像處理的庫 OpenCv import os # 讀寫文件 import shutil # 讀寫文件 # Dlib 正向人臉檢測器 / frontal face detector detector = dlib.get_frontal_face_detector() # Dlib 68 點特征預測器 / 68 points features predictor predictor = dlib.shape_predictor('data/data_dlib/shape_predictor_68_face_landmarks.dat') # OpenCv 調用攝像頭 use camera cap = cv2.VideoCapture(0) # 設置視頻參數 set camera cap.set(3, 480) # 人臉截圖的計數器 the counter for screen shoot cnt_ss = 0 # 存儲人臉的文件夾 the folder to save faces current_face_dir = "" # 保存 faces images 的路徑 the directory to save images of faces path_photos_from_camera = "data/data_faces_from_camera/" # 新建保存人臉圖像文件和數據CSV文件夾 # mkdir for saving photos and csv def pre_work_mkdir(): # 新建文件夾 / make folders to save faces images and csv if os.path.isdir(path_photos_from_camera): pass else: os.mkdir(path_photos_from_camera) pre_work_mkdir() ##### optional/可選, 默認關閉 ##### # 刪除之前存的人臉數據文件夾 # delete the old data of faces def pre_work_del_old_face_folders(): # 刪除之前存的人臉數據文件夾 # 刪除 "/data_faces_from_camera/person_x/"... folders_rd = os.listdir(path_photos_from_camera) for i in range(len(folders_rd)): shutil.rmtree(path_photos_from_camera+folders_rd[i]) if os.path.isfile("data/features_all.csv"): os.remove("data/features_all.csv") # 這里在每次程序錄入之前, 刪掉之前存的人臉數據 # 如果這里打開，每次進行人臉錄入的時候都會刪掉之前的人臉圖像文件夾 person_1/,person_2/,person_3/... # If enable this function, it will delete all the old data in dir person_1/,person_2/,/person_3/... # pre_work_del_old_face_folders() ################################## # 如果有之前錄入的人臉 / if the old folders exists # 在之前 person_x 的序號按照 person_x+1 開始錄入 / start from person_x+1 if os.listdir(path_photos_from_camera): # 獲取已錄入的最后一個人臉序號 / get the num of latest person person_list = os.listdir(path_photos_from_camera) person_num_list = [] for person in person_list: person_num_list.append(int(person.split('_')[-1])) person_cnt = max(person_num_list) # 如果第一次存儲或者沒有之前錄入的人臉, 按照 person_1 開始錄入 # start from person_1 else: person_cnt = 0 # 之后用來控制是否保存圖像的 flag / the flag to control if save save_flag = 1 # 之后用來檢查是否先按 'n' 再按 's' / the flag to check if press 'n' before 's' press_n_flag = 0 while cap.isOpened(): flag, img_rd = cap.read() # print(img_rd.shape) # It should be 480 height * 640 width kk = cv2.waitKey(1) img_gray = cv2.cvtColor(img_rd, cv2.COLOR_RGB2GRAY) # 人臉數 faces faces = detector(img_gray, 0) # 待會要寫的字體 / font to write font = cv2.FONT_HERSHEY_COMPLEX # 按下 'n' 新建存儲人臉的文件夾 / press 'n' to create the folders for saving faces if kk == ord('n'): person_cnt += 1 print("請輸入名字") person_name = input() current_face_dir = path_photos_from_camera + "person_" + str(person_cnt) os.makedirs(current_face_dir) print('\n') print("新建的人臉文件夾 / Create folders: ", current_face_dir) cnt_ss = 0 # 將人臉計數器清零 / clear the cnt of faces press_n_flag = 1 # 已經按下 'n' / have pressed 'n' # 檢測到人臉 / if face detected if len(faces) != 0: # 矩形框 / show the rectangle box for k, d in enumerate(faces): # 計算矩形大小 # we need to compute the width and height of the box # (x,y), (寬度width, 高度height) pos_start = tuple([d.left(), d.top()]) pos_end = tuple([d.right(), d.bottom()]) # 計算矩形框大小 / compute the size of rectangle box height = (d.bottom() - d.top()) width = (d.right() - d.left()) hh = int(height/2) ww = int(width/2) # 設置顏色 / the color of rectangle of faces detected color_rectangle = (255, 255, 255) # 判斷人臉矩形框是否超出 480x640 if (d.right()+ww) > 640 or (d.bottom()+hh > 480) or (d.left()-ww < 0) or (d.top()-hh < 0): cv2.putText(img_rd, "OUT OF RANGE", (20, 300), font, 0.8, (0, 0, 255), 1, cv2.LINE_AA) color_rectangle = (0, 0, 255) save_flag = 0 if kk == ord('s'): print("請調整位置 / Please adjust your position") else: color_rectangle = (255, 255, 255) save_flag = 1 # TODO 可以考慮不減 ，看效果---->結果是只有臉部圖像 cv2.rectangle(img_rd, tuple([d.left() - ww, d.top() - hh]), tuple([d.right() + ww, d.bottom() + hh]), color_rectangle, 2) # 根據人臉大小生成空的圖像 / create blank image according to the size of face detected im_blank = np.zeros((int(height*2), width*2, 3), np.uint8) if save_flag: # 按下 's' 保存攝像頭中的人臉到本地 / press 's' to save faces into local images if kk == ord('s'): # 檢查有沒有先按'n'新建文件夾 / check if you have pressed 'n' if press_n_flag: cnt_ss += 1 for ii in range(height*2): for jj in range(width*2): # 將人臉圖像填充到空圖像中 im_blank[ii][jj] = img_rd[d.top()-hh + ii][d.left()-ww + jj] cv2.imwrite(current_face_dir + "/img_face_" + str(cnt_ss) + ".jpg", im_blank) print("寫入本地 / Save into：", str(current_face_dir) + "/img_face_" + str(cnt_ss) + ".jpg") else: print("請在按 'S' 之前先按 'N' 來建文件夾 / Please press 'N' before 'S'") # 顯示人臉數 / show the numbers of faces detected cv2.putText(img_rd, "Faces: " + str(len(faces)), (20, 100), font, 0.8, (0, 255, 0), 1, cv2.LINE_AA) # 添加說明 / add some statements cv2.putText(img_rd, "Face Register", (20, 40), font, 1, (0, 0, 0), 1, cv2.LINE_AA) cv2.putText(img_rd, "N: New face folder", (20, 350), font, 0.8, (0, 0, 0), 1, cv2.LINE_AA) cv2.putText(img_rd, "S: Save current face", (20, 400), font, 0.8, (0, 0, 0), 1, cv2.LINE_AA) cv2.putText(img_rd, "Q: Quit", (20, 450), font, 0.8, (0, 0, 0), 1, cv2.LINE_AA) # 按下 'q' 鍵退出 / press 'q' to exit if kk == ord('q'): break # 如果需要攝像頭窗口大小可調 / uncomment this line if you want the camera window is resizeable # cv2.namedWindow("camera", 0) cv2.imshow("camera", img_rd) # 釋放攝像頭 / release camera cap.release() cv2.destroyAllWindows()
2、將獲取的人臉圖片轉為csv文件
import cv2 import os import dlib from skimage import io import csv import numpy as np # 要讀取人臉圖像文件的路徑q path_images_from_camera = "data/data_faces_from_camera/" # Dlib 正向人臉檢測器 detector = dlib.get_frontal_face_detector() # Dlpredictorib 人臉預測器 predictor = dlib.shape_predictor("data/data_dlib/shape_predictor_68_face_landmarks.dat") # Dlib 人臉識別模型 # Face recognition model, the object maps human faces into 128D vectors # shape_predictor_68_face_landmarks.dat face_rec = dlib.face_recognition_model_v1("data/data_dlib/dlib_face_recognition_resnet_model_v1.dat") # 返回單張圖像的 128D 特征 def return_128d_features(path_img): img_rd = io.imread(path_img) img_gray = cv2.cvtColor(img_rd, cv2.COLOR_BGR2RGB) faces = detector(img_gray, 1) print("%-40s %-20s" % ("檢測到人臉的圖像 / image with faces detected:", path_img), '\n') # 因為有可能截下來的人臉再去，檢測不出檢測來人臉了 # 所以要確保是 檢測到人臉的人臉圖像 拿去算特征 if len(faces) != 0: shape = predictor(img_gray, faces[0]) face_descriptor = face_rec.compute_face_descriptor(img_gray, shape) print("faces") else: face_descriptor = 0 print("no face") return face_descriptor # 將文件夾中照片特征提取出來, 寫入 CSV def return_features_mean_personX(path_faces_personX): features_list_personX = [] photos_list = os.listdir(path_faces_personX) if photos_list: for i in range(len(photos_list)): # 調用return_128d_features()得到128d特征 print("%-40s %-20s" % ("正在讀的人臉圖像 / image to read:", path_faces_personX + "/" + photos_list[i])) features_128d = return_128d_features(path_faces_personX + "/" + photos_list[i]) # print(features_128d) # 遇到沒有檢測出人臉的圖片跳過 if features_128d == 0: continue else: features_list_personX.append(features_128d) else: print("文件夾內圖像文件為空 / Warning: No images in " + path_faces_personX + '/', '\n') # 計算 128D 特征的均值 # personX 的 N 張圖像 x 128D -> 1 x 128D if features_list_personX: features_mean_personX = np.array(features_list_personX).mean(axis=0) else: features_mean_personX = '0' return features_mean_personX # 獲取已錄入的最后一個人臉序號 / get the num of latest person person_list = os.listdir("data/data_faces_from_camera/") person_num_list = [] for person in person_list: person_num_list.append(int(person.split('_')[-1])) person_cnt = max(person_num_list) with open("data/features_all.csv", "w", newline="") as csvfile: writer = csv.writer(csvfile) for person in range(person_cnt): # Get the mean/average features of face/personX, it will be a list with a length of 128D print(path_images_from_camera + "person_"+str(person+1)) features_mean_personX = return_features_mean_personX(path_images_from_camera + "person_"+str(person+1)) writer.writerow(features_mean_personX) print("特征均值 / The mean of features:", list(features_mean_personX)) print('\n') print("所有錄入人臉數據存入 / Save all the features of faces registered into: data/features_all.csv")
3、人臉識別
import dlib # 人臉處理的庫 Dlib import numpy as np # 數據處理的庫 numpy import cv2 # 圖像處理的庫 OpenCv import pandas as pd # 數據處理的庫 Pandas # 人臉識別模型，提取128D的特征矢量 # face recognition model, the object maps human faces into 128D vectors # Refer this tutorial: http://dlib.net/python/index.html#dlib.face_recognition_model_v1 facerec = dlib.face_recognition_model_v1("data/data_dlib/dlib_face_recognition_resnet_model_v1.dat") # 計算兩個128D向量間的歐式距離 # compute the e-distance between two 128D features def return_euclidean_distance(feature_1, feature_2): feature_1 = np.array(feature_1) feature_2 = np.array(feature_2) dist = np.sqrt(np.sum(np.square(feature_1 - feature_2))) return dist # 處理存放所有人臉特征的 csv path_features_known_csv = "data/features_all.csv" csv_rd = pd.read_csv(path_features_known_csv, header=None) # 用來存放所有錄入人臉特征的數組 # the array to save the features of faces in the database features_known_arr = [] # 讀取已知人臉數據 # print known faces for i in range(csv_rd.shape[0]): features_someone_arr = [] for j in range(0, len(csv_rd.ix[i, :])): features_someone_arr.append(csv_rd.ix[i, :][j]) features_known_arr.append(features_someone_arr) print("Faces in Database：", len(features_known_arr)) # Dlib 檢測器和預測器 # The detector and predictor will be used detector = dlib.get_frontal_face_detector() predictor = dlib.shape_predictor('data/data_dlib/shape_predictor_68_face_landmarks.dat') # 創建 cv2 攝像頭對象 # cv2.VideoCapture(0) to use the default camera of PC, # and you can use local video name by use cv2.VideoCapture(filename) cap = cv2.VideoCapture(0) # cap.set(propId, value) # 設置視頻參數，propId 設置的視頻參數，value 設置的參數值 cap.set(3, 480) # cap.isOpened() 返回 true/false 檢查初始化是否成功 # when the camera is open while cap.isOpened(): flag, img_rd = cap.read() kk = cv2.waitKey(1) # 取灰度 img_gray = cv2.cvtColor(img_rd, cv2.COLOR_RGB2GRAY) # 人臉數 faces faces = detector(img_gray, 0) # 待會要寫的字體 font to write later font = cv2.FONT_HERSHEY_COMPLEX # 存儲當前攝像頭中捕獲到的所有人臉的坐標/名字 # the list to save the positions and names of current faces captured pos_namelist = [] name_namelist = [] # 按下 q 鍵退出 # press 'q' to exit if kk == ord('q'): break else: # 檢測到人臉 when face detected if len(faces) != 0: # 獲取當前捕獲到的圖像的所有人臉的特征，存儲到 features_cap_arr # get the features captured and save into features_cap_arr features_cap_arr = [] for i in range(len(faces)): shape = predictor(img_rd, faces[i]) features_cap_arr.append(facerec.compute_face_descriptor(img_rd, shape)) # 遍歷捕獲到的圖像中所有的人臉 # traversal all the faces in the database for k in range(len(faces)): print("##### camera person", k+1, "#####") # 讓人名跟隨在矩形框的下方 # 確定人名的位置坐標 # 先默認所有人不認識，是 unknown # set the default names of faces with "unknown" name_namelist.append("unknown") # 每個捕獲人臉的名字坐標 the positions of faces captured pos_namelist.append(tuple([faces[k].left(), int(faces[k].bottom() + (faces[k].bottom() - faces[k].top())/4)])) # 對於某張人臉，遍歷所有存儲的人臉特征 # for every faces detected, compare the faces in the database e_distance_list = [] for i in range(len(features_known_arr)): # 如果 person_X 數據不為空 if str(features_known_arr[i][0]) != '0.0': print("with person", str(i + 1), "the e distance: ", end='') e_distance_tmp = return_euclidean_distance(features_cap_arr[k], features_known_arr[i]) print(e_distance_tmp) e_distance_list.append(e_distance_tmp) else: # 空數據 person_X e_distance_list.append(999999999) # Find the one with minimum e distance similar_person_num = e_distance_list.index(min(e_distance_list)) print("Minimum e distance with person", int(similar_person_num)+1) if min(e_distance_list) < 0.4: # 在這里修改 person_1, person_2 ... 的名字 # 可以在這里改稱 Jack, Tom and others # Here you can modify the names shown on the camera name_namelist[k] = "Person "+str(int(similar_person_num)+1) print("May be person "+str(int(similar_person_num)+1)) else: print("Unknown person") # 矩形框 # draw rectangle for kk, d in enumerate(faces): # 繪制矩形框 cv2.rectangle(img_rd, tuple([d.left(), d.top()]), tuple([d.right(), d.bottom()]), (0, 255, 255), 2) print('\n') # 在人臉框下面寫人臉名字 # write names under rectangle for i in range(len(faces)): cv2.putText(img_rd, name_namelist[i], pos_namelist[i], font, 0.8, (0, 255, 255), 1, cv2.LINE_AA) print("Faces in camera now:", name_namelist, "\n") cv2.putText(img_rd, "Press 'q': Quit", (20, 450), font, 0.8, (84, 255, 159), 1, cv2.LINE_AA) cv2.putText(img_rd, "Face Recognition", (20, 40), font, 1, (0, 0, 0), 1, cv2.LINE_AA) cv2.putText(img_rd, "Faces: " + str(len(faces)), (20, 100), font, 1, (0, 0, 255), 1, cv2.LINE_AA) # 窗口顯示 show with opencv cv2.imshow("camera", img_rd) # 釋放攝像頭 release camera cap.release() # 刪除建立的窗口 delete all the windows cv2.destroyAllWindows()
完畢！
聲明：代碼是github以為博主的，本人只是拿着學習人臉識別，為了尊重博主，貼出其代碼地址：https://github.com/coneypo/Dlib_face_recognition_from_camera